End a browser session
AI agents invoke browser.end_session to trigger actions in MCP Fullstack. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Ending a browser session terminates an active browser automation session, which is an external operation with real side effects (closing the session, releasing resources, potentially losing unsaved state). It doesn't just read data, nor does it irreversibly delete persistent data. It's an operational action on a running process, making Execute the most appropriate category.
From the tool's definition End a browser session
Attacks that exploit this kind of access
End a browser session. It is categorised as a Execute tool in the MCP Fullstack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for browser.end_session: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Fullstack. Nothing to install.
browser.end_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser.end_session rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser.end_session. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser.end_session is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →